Sample-Optimal Zero-Violation Safety For Continuous Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ray, Ritabrata, Nakahira, Yorie, Kar, Soummya
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910365515776000
author Ray, Ritabrata
Nakahira, Yorie
Kar, Soummya
author_facet Ray, Ritabrata
Nakahira, Yorie
Kar, Soummya
contents In this paper, we study the problem of ensuring safety with a few shots of samples for partially unknown systems. We first characterize a fundamental limit when producing safe actions is not possible due to insufficient information or samples. Then, we develop a technique that can generate provably safe actions and recovery behaviors using a minimum number of samples. In the performance analysis, we also establish Nagumos theorem - like results with relaxed assumptions, which is potentially useful in other contexts. Finally, we discuss how the proposed method can be integrated into a policy gradient algorithm to assure safety and stability with a handful of samples without stabilizing initial policies or generative models to probe safe actions.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06045
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sample-Optimal Zero-Violation Safety For Continuous Control
Ray, Ritabrata
Nakahira, Yorie
Kar, Soummya
Systems and Control
In this paper, we study the problem of ensuring safety with a few shots of samples for partially unknown systems. We first characterize a fundamental limit when producing safe actions is not possible due to insufficient information or samples. Then, we develop a technique that can generate provably safe actions and recovery behaviors using a minimum number of samples. In the performance analysis, we also establish Nagumos theorem - like results with relaxed assumptions, which is potentially useful in other contexts. Finally, we discuss how the proposed method can be integrated into a policy gradient algorithm to assure safety and stability with a handful of samples without stabilizing initial policies or generative models to probe safe actions.
title Sample-Optimal Zero-Violation Safety For Continuous Control
topic Systems and Control
url https://arxiv.org/abs/2403.06045